297c580a2d2da2839d936437bf4e3a4c64034950 |
|
07-Oct-2017 |
I-Jui (Ray) Sung <ijsung@google.com> |
Revise tests so weights and biases are no longer inputs This CL turn them into constant operands set at model building time. Also fixed problems in the test generator on handling FP literals in model paramters. Original tests are renamed with _weights_as_inputs suffix. Bug: 67015862 Bug: 63905942 Test: NeuralNetworksTests on Angler Change-Id: Ic59c78e7e6fcb143fb05a0360baa281b7528050c
/frameworks/ml/nn/runtime/test/specs/conv_quant8.mod.py
|
238a880d67b3aa5650ad52037fe1c25b1750eca9 |
|
05-Oct-2017 |
Miao Wang <miaowang@google.com> |
Fix quantized CONV_2D and FULLY_CONNECTED tests and add more validation for input tensor types. Bug: 67430183 Bug: 63905942 Test: mm Test: NeuralNetworksTest on sailfish Change-Id: Ibc52ba04ebc515d9208b9266a2e9bbe90d675542
/frameworks/ml/nn/runtime/test/specs/conv_quant8.mod.py
|
b2e34b735db694efd1b32609beffa2a74258789d |
|
03-Oct-2017 |
leozwang <leozwang@google.com> |
Add conv 2d float large tests. Bug: 63905942 Test: local test. NeuralNetworksTest on Pixel. Change-Id: I27ce0fc8d7e55991b70eaf574a17b55b2c4f4844
/frameworks/ml/nn/runtime/test/specs/conv_quant8.mod.py
|
45bf79e5b9fee354fde7c1f64417d9ca4a1da7da |
|
25-Sep-2017 |
Miao Wang <miaowang@google.com> |
Clarify the expectation of scale and zeroPoint for affected ops. - Remove the OperandType constructor taking f_min and f_max as quantization parameters as it causes confusions for ops like LOGISTIC and SOFTMAX. - Update the documenation to clearly state the expected scale and zeroPoint for LOGISTIC, SOFTMAX and CONCATENATION. - Update the tests to directly input scale and zeroPoint. Bug: 63905942 Test: mm Test: NeuralNetworksTest pass Change-Id: Ia450d6ce9509205d22e6383bd7e454afa0568cbb
/frameworks/ml/nn/runtime/test/specs/conv_quant8.mod.py
|
ca5f11deb6d1ae8e8d8b5bd7586b801c0d2654fb |
|
12-Sep-2017 |
gfan <gfan@google.com> |
Add unit tests for op CONV_2D for Quant8 and Float32 Test: NeuralNetworksTest on Pixel XL Bug: 63905942 Change-Id: I8e6f902975901608ab2d0932bbb3ac6b16ffa60e
/frameworks/ml/nn/runtime/test/specs/conv_quant8.mod.py
|